# Set the random seed value
np.random.seed(42)
# Choose data and model size
num_patterns = 100
data_dim = 200
# Get dataset
train_data = np.float64(
np.random.random_integers(0, 1, (num_patterns, data_dim)))
train_label = np.float64(
np.random.random_integers(0, 1, (num_patterns, data_dim)))
# Choose activation function
act = actFct.Sigmoid()
# Train model, this performs a single trial as shown in Figure 8 a) in the Hebbina descent paper
mymodel, results = train_Hebbian_descent_model(train_data=train_data,
train_label=train_label,
centered=True,
act=actFct.Sigmoid(),
epochs=1,
epsilon=0.2,
batch_size=1,
weightdecay=0.0)
# Display errors
vis.xlabel("Pattern index (" + str(num_patterns) + " = latest pattern)")
vis.ylabel("Mean Absolute Error")
# Split in tarining and test data
train_data = data[0:50000]
test_data = data[50000:70000]
# Set hyperparameters batchsize and number of epochs
batch_size = 10
max_epochs = 20
# Create model with sigmoid hidden units, linear output units, and squared error.
ae = aeModel.AutoEncoder(
v1 * v2,
h1 * h2,
data=train_data,
visible_activation_function=act.Identity(),
hidden_activation_function=act.Sigmoid(),
cost_function=cost.SquaredError(),
initial_weights=0.01,
initial_visible_bias=0.0,
initial_hidden_bias=-2.0,
# Set initially the units to be inactive, speeds up learning a little bit
initial_visible_offsets=0.0,
initial_hidden_offsets=0.02,
dtype=numx.float64)
# Initialized gradient descent trainer
trainer = aeTrainer.GDTrainer(ae)
# Train model
print 'Training'
print 'Epoch\tRE train\t\tRE test\t\t\tSparsness train\t\tSparsness test '
h1 = 10
h2 = 10
# Load data , get it from 'deeplearning.net/data/mnist/mnist.pkl.gz'
train_data, _, _, _, test_data, _ = io.load_mnist("../../data/mnist.pkl.gz",
False)
# Set hyperparameters batchsize and number of epochs
batch_size = 10
max_epochs = 10
# Create model with sigmoid hidden units, linear output units, and squared error loss.
ae = aeModel.AutoEncoder(v1 * v2,
h1 * h2,
data=train_data,
visible_activation_function=act.Sigmoid(),
hidden_activation_function=act.Sigmoid(),
cost_function=cost.CrossEntropyError(),
initial_weights='AUTO',
initial_visible_bias='AUTO',
initial_hidden_bias='AUTO',
initial_visible_offsets='AUTO',
initial_hidden_offsets='AUTO',
dtype=numx.float64)
# Initialized gradient descent trainer
trainer = aeTrainer.GDTrainer(ae)
# Train model
print 'Training'
print 'Epoch\tRE train\t\tRE test\t\t\tSparsness train\t\tSparsness test '